An ANN algorithm for automatic, real-time tsunami detection in deep-sea level measurements

The present paper looks at algorithms to be implemented in the software of bottom pressure recorders (BPRs) for the automatic, real-time detection of a tsunami within recorded signals. The structure of an algorithm based on the use of an artificial neural network (ANN) is presented and compared to the one developed under the Deep-ocean Assessment and Reporting of Tsunamis (DART) program run by the U.S. National Oceanic and Atmospheric Administration (NOAA). The performance and efficiency of the two algorithms are compared using both synthetic and actually measured time series. Results show that an improvement in detection performance can be obtained by using the ANN algorithm.